Building material performance monitoring method and system

Abstract

The invention relates to the technical field of building material monitoring, in particular to a building material performance monitoring method and system, and the method comprises the following steps: S1, collecting and transmitting building material data through a sensor; s2, preprocessing the data and generating a comprehensive performance degradation index; s3, optimizing the acquisition frequency of the sensor, and calling the LSTM model to predict the service life; and S4, judging whether the building material is qualified or not, and if not, performing early warning. The beneficial effects of the invention are that the system can adjust the collection frequency of the sensor, monitors the data of the building material in real time, and predicts the predicted life of the building material through the LSTM model.

Description

Technical Field

[0001] The present invention relates to the technical field of building material monitoring, and particularly to a method and system for monitoring the performance of building materials. Background Art

[0002] With the progress of society and the development of economy, the construction industry is constantly developing towards higher, more complex and more functional directions. From masonry buildings to skyscrapers, long-span bridges and various special-function buildings such as hospitals and laboratories, the performance requirements for building materials are getting higher and higher. Affected by natural environmental factors such as wind and rain erosion, temperature changes, chemical corrosion, etc., timely monitoring of building materials can reduce the costs of building maintenance and reconstruction, and ensure the safe use of buildings within their designed service life.

[0003] In the prior art, the monitoring of building material performance mostly adopts manual inspection or fixed-point detection by a single sensor, which has problems of poor data timeliness and single monitoring parameters, and it is difficult to meet the real-time monitoring requirements of the durability and safety of materials for modern buildings. Summary of the Invention

[0004] Aiming at the deficiencies of the prior art, the present application proposes a method and system for monitoring the performance of building materials, which can adjust the sensor acquisition frequency, monitor building material data in real time, and predict the predicted life of building materials through an LSTM model.

[0005] The following is the technical solution of the present invention. A method for monitoring the performance of building materials includes the following steps:

[0006] S1. Sensors collect and transmit building material data;

[0007] S2. Preprocess the data and generate a comprehensive performance degradation index;

[0008] S3. Optimize the sensor acquisition frequency and call the LSTM model to predict the life;

[0009] S4. Judge whether the building materials are qualified. If not, give an early warning.

[0010] As a preferred solution of the present invention, in S1, the building material data includes temperature, humidity, stress parameters, vibration parameters and corrosion rate parameters.

[0011] As a preferred solution of the present invention, in S2, data normalization processing is performed, and the expression is as follows:

[0012]

[0013] In the above formula, X norm is the converted data, X is the original data, X max is the historical maximum value of the original data, Xmin is the historical minimum value of the original data.

[0014] As a preferred solution of the present invention, in S2, a comprehensive performance degradation index is generated, and the expression is as follows:

[0015] D = α·S + β·C + γ·V

[0016] In the above formula, D is the comprehensive performance degradation index, S is the stress parameter, C is the corrosion rate parameter, V is the vibration parameter, and α, β, and γ are weight coefficients based on material properties.

[0017] As a preferred solution of the present invention, in S3, the sensor acquisition frequency is optimized, and the expression is as follows:

[0018]

[0019] In the above formula, f i is the acquisition frequency, E i is the remaining battery power, E total is the total battery power, ΔD i is the performance degradation rate, and Δt is the time interval used when calculating the performance degradation rate.

[0020] As a preferred solution of the present invention, in S4, the situations where building materials are unqualified include:

[0021] at least one of the temperature, humidity, stress parameter, vibration parameter, and corrosion rate parameter does not meet the building material data threshold;

[0022] or, the comprehensive performance degradation index is greater than the comprehensive performance degradation index threshold;

[0023] or, the predicted life is lower than the safety life.

[0024] As a preferred solution of the present invention, in S4, it further includes: when giving an early warning, triggering a smart contract to upload the hash value of the over-limit data, including the following steps:

[0025] S41. Generate the hash value of the key data;

[0026] H = SHA256(D raw ||D pro || timestamp)

[0027] In the above formula, H is the hash value, D raw is the original data, D pro is the processed result data, and || represents concatenation.

[0028] S42. Automatically call the smart contract to upload the hash value to the blockchain when giving an early warning, and generate a certificate block containing the timestamp and location information.

[0029] A building material performance monitoring system, comprising:

[0030] A sensing module, configured to collect building material data and connect to a central controller;

[0031] A central controller, configured to receive and process building material data and connect to the sensing module;

[0032] A cloud server, configured to store historical data and run a machine learning model for predicting material performance degradation, and connect to the central controller;

[0033] A mobile terminal, configured to set building material data thresholds and display a visualization interface, and connect to the cloud server.

[0034] As a preferred solution of the present invention, the sensing module is connected to the central controller through the LoRa wireless transmission protocol.

[0035] As a preferred solution of the present invention, the cloud server is connected to the central controller through the MQTT protocol.

[0036] The beneficial effects of the present invention are as follows: By monitoring the temperature, humidity, stress parameters, vibration parameters, and corrosion rate parameters of building materials, the building material data is monitored in real time. The building material data is compared with the corresponding thresholds, and a comprehensive performance degradation index is constructed to evaluate the qualification of building materials. The predicted life of building materials is predicted through the LSTM model; by optimizing the sensor network deployment strategy, the real-time performance of sensor data acquisition is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a schematic diagram of the monitoring system of the present invention;

[0038] Figure 2 It is a flowchart of the monitoring method of the present invention;

[0039] Figure 3 It is a step diagram of the detection method of the present invention;

[0040] In the figure: 1. Sensing module; 2. Central controller; 3. Cloud server; 4. Mobile terminal; 5. Temperature and humidity sensor; 6. Stress sensor; 7. Corrosion test electrode; 8. Vibration accelerometer. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] To make the technical problems solved, the technical solutions adopted, and the technical effects achieved by the present invention clearer, the technical solutions of the embodiments of the present invention will be further described in detail below with reference to the drawings. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts fall within the protection scope of the present invention.

[0042] Example 1:

[0043] As Figure 1 shown, a building material performance monitoring system includes:

[0044] A sensing module 1, used to collect building material data and connect to the central controller 2;

[0045] A central controller 2, used to receive and process building material data and connect to the sensing module 1;

[0046] A cloud server 3, used to store historical data and run a machine learning model for predicting material performance degradation, and connect to the central controller 2;

[0047] A mobile terminal 4, used to set building material data thresholds and display a visualization interface, and connect to the cloud server 3.

[0048] In this embodiment, the sensing module 1 includes a temperature and humidity sensor 5, a stress sensor 6, a corrosion test electrode 7, and a vibration accelerometer 8. Among them, the temperature and humidity sensor 5 is arranged on the surface or inside of the building material to collect the temperature and humidity of the building material; the stress sensor 6 is arranged inside the building material to collect the stress data of the building material, the corrosion test electrode 7 is arranged at a position of the building material close to the metal component to monitor the corrosion rate parameter of the building material, and the vibration accelerometer 8 is arranged inside the building material to monitor the vibration parameter of the building material. The sensing module 1 is connected to the central controller 2 through the LoRa wireless transmission protocol.

[0049] In this embodiment, the central controller 2 integrates an STM32 series microprocessor and an FPGA chip, receives building material data, and performs preprocessing such as noise filtering and data normalization on the building material data, and uses edge computing technology to preliminarily determine abnormal data.

[0050] In this embodiment, the cloud server 3 is built based on a distributed database, used to store historical data and run a machine learning model for predicting material performance degradation, and is connected to the central controller 2 through the MQTT protocol.

[0051] In this embodiment, the mobile terminal 4 customizes the building material data threshold and is provided with a visualization interface, and the visualization interface displays real-time monitoring data and generates a warning report.

[0052] Set a building material data threshold on the mobile terminal 4, and synchronously transmit the building material data threshold to the cloud server 3. The sensing module 1 collects the building material data and transmits the building material data to the central controller 2. The central controller 2 receives and processes the building material data, and transmits the processed building material data to the cloud server 3. The cloud server 3 stores the historical data and runs a machine learning model to predict the degradation of material performance, outputs the predicted life of the building material, compares the building material data with the building material data threshold, and determines whether the predicted life is lower than the safe life. If the building material data does not meet the building material data threshold or the predicted life is lower than the safe life, warning content is transmitted to the mobile terminal 4. The mobile terminal 4 is provided with a visualization interface, and the visualization interface displays real-time monitoring data and generates a warning report for the operator to view.

[0053] Embodiment 2:

[0054] As Figure 2 and Figure 3 shown, a method for monitoring the performance of building materials includes the following steps:

[0055] S1. Data collection and transmission;

[0056] The sensor collects the building material data at an adaptive frequency and uploads it through the optimized wireless network;

[0057] S2. Data preprocessing;

[0058] Perform normalization, noise filtering, and generate a comprehensive performance degradation index D;

[0059] S3. Performance analysis and prediction;

[0060] The cloud platform calls the LSTM model to predict the evolution trend of D, and at the same time optimizes the sensor network deployment strategy.

[0061] S4. Dynamic warning and feedback;

[0062] Trigger the smart contract to chain the hash value of the over-limit data and push multi-level alarms.

[0063] In step S1, for data collection and transmission. Specifically, the sensor collects the building material data at an adaptive frequency. The building material data includes parameters such as the surface temperature, humidity, internal stress, vibration, and corrosion rate of the material, and uploads it to the controller through the wireless network.

[0064] In step S2, for data preprocessing. Specifically, perform normalization, noise filtering, and generate a comprehensive performance degradation index D, including the following steps:

[0065] S21. Data normalization processing;

[0066] Perform unified dimension conversion on the stress parameters, vibration parameters, and corrosion rate parameters collected by the sensors. The normalization expression is as follows:

[0067]

[0068] In the above formula, X norm is the converted data, X is the original data, X max is the historical maximum value of the original data, X min is the historical minimum value of the original data.

[0069] S22. Weighted fusion calculation;

[0070] Construct a comprehensive performance degradation index D, and the expression is as follows:

[0071] D = α·S + β·C + γ·V

[0072] In the above formula, D is the comprehensive performance degradation index, S is the stress parameter, C is the corrosion rate parameter, V is the vibration parameter, and α, β, and γ are weight coefficients based on material properties.

[0073] S23. Degradation threshold determination;

[0074] When D > D th an alarm is triggered, D th is the threshold of the comprehensive performance degradation index, and D th is determined and adjusted based on the material type and historical failure data.

[0075] In step S3, performance analysis and prediction. Specifically, the cloud platform calls the LSTM model to predict the evolution trend of D, and at the same time optimizes the sensor network deployment strategy. The cloud platform calls the trained LSTM model, inputs historical data and real-time data, outputs the predicted life of the material and the safety level assessment result, and optimizes the sensor network deployment strategy to improve the real-time performance of sensor data collection.

[0076] Calculate the remaining power E i of each sensor node in real time, and dynamically adjust the acquisition frequency f i . The expression is as follows:

[0077]

[0078] In the above formula, f i is the acquisition frequency, E i is the remaining power, E total is the total power, ΔD i is the performance degradation rate, and Δt is the time interval used when calculating the performance degradation rate.

[0079] In step S4, dynamic warning and feedback are performed. Specifically, when the monitored parameters are not within the preset threshold range or the predicted lifespan is lower than the safe lifespan, the system triggers multi-level alarms, generates a maintenance recommendation plan, triggers the smart contract to upload the hash value of the over-limit data to the blockchain, and pushes multi-level alarms. When at least one of the temperature, humidity, stress parameter, vibration parameter, and corrosion rate parameter does not meet the building material data threshold, or the comprehensive performance degradation index is greater than the comprehensive performance degradation index threshold, or the predicted lifespan is lower than the safe lifespan, the system triggers multi-level alarms, and alarms through an interface pop-up window on the mobile terminal 4 and sends text messages to the operator's mobile phone.

[0080] When warning, trigger the smart contract to upload the hash value of the over-limit data to the blockchain, including the following steps:

[0081] S41. Generate the hash value of the key data;

[0082] Generate the SHA-256 hash value for the original data and processed result data of the sensor. The expression is as follows:

[0083] H = SHA256(D raw ||D pro || timestamp)

[0084] In the above formula, H is the hash value, D raw is the original data, D pro is the processed result data, and || represents concatenation.

[0085] S42. Trigger the smart contract to upload the hash value to the blockchain;

[0086] When the monitored data exceeds the threshold, automatically call the smart contract to upload the hash value to the blockchain and generate a certification block containing the timestamp and location information;

[0087] S43. Cross-chain verification;

[0088] Associate the blockchain certification with the local database through the IPFS distributed storage technology for a third-party institution to verify the data integrity through the API interface.

[0089] The present invention sets data storage and optimization. The time-series database is used to store the original data and analysis results, and the machine learning model parameters are updated regularly to improve the prediction accuracy. The original data, fusion index, and blockchain certification records are stored, and the model parameters and network configuration are updated regularly.

[0090] The present invention monitors the temperature, humidity, stress parameters, vibration parameters, and corrosion rate parameters of building materials, monitors the building material data in real time, compares the building material data with the corresponding thresholds, constructs a comprehensive performance degradation index to evaluate the qualification of building materials, and predicts the predicted life of building materials through an LSTM model; by optimizing the sensor network deployment strategy, the real-time performance of sensor data collection is improved.

[0091] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concepts. Obviously, those skilled in the art can make various changes and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the equivalent technology of the present invention, the present invention is also intended to include these modifications and variations.

Claims

1. A method for monitoring the performance of building materials, characterized in that, It includes the following steps: S1. The sensor collects and transmits building material data; S2. The data is preprocessed and a comprehensive performance degradation index is generated; S3. Optimize the sensor acquisition frequency and call the LSTM model to predict the lifespan; S4. Determine whether the building materials are qualified. If not, give an alarm.

2. The method for monitoring the performance of a building material according to claim 1, wherein, In S1, the building material data includes temperature, humidity, stress parameters, vibration parameters, and corrosion rate parameters.

3. A method for monitoring the performance of building materials according to claim 1, characterized in that, In S2, the data is normalized, and the expression is as follows: In the above formula, X norm is the converted data, X is the original data, X max is the historical maximum value of the original data, X min is the historical minimum value of the original data.

4. A method for monitoring the performance of a building material according to claim 1, characterized in that, In S2, a comprehensive performance degradation index is generated, and the expression is as follows: D = α·S + β·C + γ·V In the above formula, D is the comprehensive performance degradation index, S is the stress parameter, C is the corrosion rate parameter, V is the vibration parameter, and α, β, and γ are weight coefficients based on material properties.

5. A method for monitoring the performance of a building material according to claim 1, characterized in that, In S3, the sensor acquisition frequency is optimized, and the expression is as follows: In the above formula, f i is the acquisition frequency, E i is the remaining battery level, E total is the total battery level, ΔD i is the performance degradation rate, and Δt is the time interval used when calculating the performance degradation rate.

6. A method for monitoring the performance of a building material according to claim 1, characterized in that, In S4, the situations where the building materials are unqualified include: At least one of the temperature, humidity, stress parameters, vibration parameters, and corrosion rate parameters does not meet the building material data threshold; Or, the comprehensive performance degradation index is greater than the comprehensive performance degradation index threshold; Or, the predicted lifespan is lower than the safe lifespan.

7. A method for monitoring the performance of building materials according to claim 1, characterized in that, In S4, it also includes: When giving an alarm, trigger the smart contract to upload the hash value of the over-limit data, including the following steps: S41. Generate the hash value of the key data; H = SHA256(D raw || D pro || Timestamp) In the above formula, H is the hash value, D raw is the original data, D pro is the processed result data, and || represents concatenation. S42. Automatically call the smart contract to upload the hash value to the chain when giving an alarm, and generate a deposit block containing the timestamp and location information.

8. A building material performance monitoring system, applicable to the building material performance monitoring method described in any one of claims 1-7, characterized in that, It includes: A sensing module, which is used to collect building material data and connect to the central controller; A central controller, which is used to receive and process building material data and connect to the sensing module; A cloud server, which is used to store historical data and run a machine learning model for predicting material performance degradation, and connect to the central controller; A mobile terminal, which is used to set the building material data threshold and display a visualization interface, and connect to the cloud server.

9. The performance monitoring system for a building material according to claim 8, characterized in that, The sensing module is connected to the central controller through the LoRa wireless transmission protocol.

10. The performance monitoring system for a building material according to claim 8, characterized in that, The cloud server is connected to the central controller through the MQTT protocol.

Images